Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Statistical Software for Data Analysis and Clinical Trials01:12

Statistical Software for Data Analysis and Clinical Trials

Statistical software is pivotal in data analysis and clinical trials by providing tools to analyze data, draw conclusions, and make predictions. These software packages range from simple data management applications to complex analytical platforms, supporting various statistical tests, models, and simulation techniques. Their significance lies in their ability to handle vast amounts of data with precision and efficiency, enabling researchers to validate hypotheses, identify trends, and make...
Biostatistics: Overview01:20

Biostatistics: Overview

Biostatistics plays a crucial role in understanding and analyzing data in healthcare and biology. Biostatisticians conduct experiments, gather evidence, and draw meaningful conclusions using statistical methods and techniques. Different variables form the foundation of biostatistical analysis, allowing researchers to understand and interpret data effectively. These variables are classified into different types, each serving a specific purpose in statistical analysis.
Discrete variables are...
Evolutionary Relationships through Genome Comparisons02:54

Evolutionary Relationships through Genome Comparisons

Genome comparison is one of the excellent ways to interpret the evolutionary relationships between organisms. The basic principle of genome comparison is that if two species share a common feature, it is likely encoded by the DNA sequence conserved between both species. The advent of genome sequencing technologies in the late 20th century enabled scientists to understand the concept of conservation of domains between species and helped them to deduce evolutionary relationships across diverse...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

[Investigation of antidepressant active components and mechanisms of total triterpenoids of Wolfiporia cocos based on serum pharmacochemistry combined with network pharmacology and experimental validation].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2026
Same author

Repositioning renal denervation in resistant hypertension: evidence-based insights, stratified decision-making, and implementation pathways.

Frontiers in cardiovascular medicine·2026
Same author

Defining active conformations from substrate-bound structures enables active-state AlphaFold2 modeling of all 437 human catalytic protein kinase domains.

The Biochemical journal·2026
Same author

Jingangteng Capsule Attenuates Ulcerative Colitis via Maintaining the Homeostasis of Intestinal Microbiota and Metabolites, Inhibiting the PI3K-AKT-mTOR Signaling Pathway.

Pharmaceuticals (Basel, Switzerland)·2026
Same author

Structural mechanism for noncanonical GPCR signaling in the Hedgehog pathway.

Nature structural & molecular biology·2026
Same author

Hydrogel-based co-culture and application of two types of islet cells.

PloS one·2026

Related Experiment Video

Updated: May 9, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

The role of balanced training and testing data sets for binary classifiers in bioinformatics.

Qiong Wei1, Roland L Dunbrack

  • 1Institute for Cancer Research, Fox Chase Cancer Center, Philadelphia, Pennsylvania, United States of America.

Plos One
|July 23, 2013
PubMed
Summary
This summary is machine-generated.

Training machine learning models with balanced data improves prediction accuracy for binary classification tasks, even with imbalanced real-world datasets. Balanced training, using 50% of each class, enhances performance metrics like balanced accuracy and Matthews correlation coefficient.

More Related Videos

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets
03:37

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets

Published on: March 1, 2024

Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

Related Experiment Videos

Last Updated: May 9, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets
03:37

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets

Published on: March 1, 2024

Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

Area of Science:

  • Bioinformatics
  • Machine Learning
  • Genomics

Background:

  • Machine learning model performance in binary classification is sensitive to outcome proportions in training data.
  • Real-world applications often involve imbalanced datasets or unknown outcome proportions, posing challenges for accurate prediction.

Purpose of the Study:

  • To investigate the impact of training data proportions on machine learning model performance for binary classification.
  • To determine the optimal training data strategy for predicting human missense mutation phenotypes, where outcome proportions are unknown.

Main Methods:

  • Evaluated machine learning models using both balanced (50/50) and imbalanced training datasets.
  • Tested model performance on datasets with varying proportions of the two outcomes.
  • Assessed performance using balanced accuracy, Matthews correlation coefficient, and area under ROC curves.

Main Results:

  • Balanced training data (50% neutral, 50% deleterious) consistently yielded superior performance across all tested metrics.
  • This finding held true regardless of the outcome proportions present in the testing data.
  • Balanced accuracy, Matthews correlation coefficient, and AUC were maximized with balanced training sets.

Conclusions:

  • Using balanced training data is crucial for robust machine learning model performance in binary classification, particularly for imbalanced datasets.
  • The strategy of balancing training data, e.g., 50% for each class, is recommended for predicting missense mutation phenotypes and other imbalanced biological prediction problems.
  • While other techniques exist, data balancing offers a reliable approach to mitigate performance issues caused by class imbalance.